Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space
This work aims to improve the accuracy of knowledge tracing for students by better capturing hierarchical cognitive states and individualized problem difficulty perception, which is an incremental improvement for educational technology.
This paper addresses limitations in existing Knowledge Tracing (KT) methods by proposing L-HAKT, which uses an LLM-powered teacher agent to parse question semantics and construct hierarchical knowledge dependencies, and a student agent to simulate learning behaviors. It then applies contrastive learning in hyperbolic space to align synthetic and real data, explicitly modeling the tree-like hierarchical structure of knowledge points and characterizing learning curve differences at various levels.
Knowledge Tracing (KT) diagnoses students' concept mastery through continuous learning state monitoring in education.Existing methods primarily focus on studying behavioral sequences based on ID or textual information.While existing methods rely on ID-based sequences or shallow textual features, they often fail to capture (1) the hierarchical evolution of cognitive states and (2) individualized problem difficulty perception due to limited semantic modeling. Therefore, this paper proposes a Large Language Model Hyperbolic Aligned Knowledge Tracing(L-HAKT). First, the teacher agent deeply parses question semantics and explicitly constructs hierarchical dependencies of knowledge points; the student agent simulates learning behaviors to generate synthetic data. Then, contrastive learning is performed between synthetic and real data in hyperbolic space to reduce distribution differences in key features such as question difficulty and forgetting patterns. Finally, by optimizing hyperbolic curvature, we explicitly model the tree-like hierarchical structure of knowledge points, precisely characterizing differences in learning curve morphology for knowledge points at different levels. Extensive experiments on four real-world educational datasets validate the effectiveness of our Large Language Model Hyperbolic Aligned Knowledge Tracing (L-HAKT) framework.